High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Solar Radiation Prediction using Adaboost Algorithm


D.Kamalasri , Prathyusha Institute of Technology; J.Arun Prasath , Prathyusha Institute of Technology; R.Thandaiah Prabu, Prathyusha Institute of Technology


Solar Radiation Prediction, Adaboost


Predictions of incoming solar energy are acquiring more importance, because of strong increment of solar power generation. Predictions is very useful in solar energy applications because it permits to generate solar data for locations where measurements are not available. In existing systems, solar radiation is predicted using fuzzy logic and neural networks separately. So that Mean absolute percentage error is greater than 10%. Fuzzy logic and neural networks are combined together using Takagi Sugeno Kang (TSK) method. TSK method is very efficient than mamdani method. Previous year solar radiation data is collected from National Environmental Agency and using this values neural network was trained. The graph between measured and predicted data values was plotted .Error is calculated using the difference between desired and output value. Prediction using combination of fuzzy and neural network model having Mean Absolute Percentage Error 6% was achieved. But in order to reduce Absolute Percentage Error value, we need to check the validity of the input data, so, that Adaboost algorithm is introduced in our proposed method. Adaboost algorithm is one of the best method of classification of weak learners. The algorithm classifies the training and testing data and also produces the corresponding errors. After finding the errors, it will be neglected from input data to make the predicted with more accuracy and less error. So that Mean Absolute Percentage Error -2.33% was achieved.

Other Details

Paper ID: IJSRDV3I40522
Published in: Volume : 3, Issue : 4
Publication Date: 01/07/2015
Page(s): 858-860

Article Preview

Download Article